GTR: Gated Token Recurrence for Efficient Dense Prediction
Open paper
Benchmark
Model
Rank
Results
instance-segmentation-on-coco-minival
GTR-X
#28
mask AP: 49.8
object-detection-on-coco-val2017
GTR-X
#37
box AP: 59.4
human-pose-keypoint-estimation-on-coco-val2017
GTR-X
#53
AP: 75.5
Rank counts only results with a code link.